2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 18 , Issue 1 , PP: 80-102, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Rasha Khalid Ibrahim 1 * , Mays M. Hoobi 2
Doi: https://doi.org/10.54216/JISIoT.180106
As people increasingly rely on computers to store sensitive information and interact with various technologies, the need for low-cost, effective security measures has become more critical than ever. One such method is keystroke dynamics, which analyzes a person’s typing rhythm on digital devices. This behavioral biometric approach enhances the security and reliability of user authentication systems and contributes to improved cybersecurity. This study aims to reduce authentication risks by encouraging the adoption of keystroke-based verification methods. The research uses a fixed-text password dataset (.tie5Roanl), collected from 51 users who typed the password over eight sessions conducted on alternating days, capturing variations in mood and typing behavior. Seven models were developed, each following a structured seven-phase process. The first phase involved loading the CMU Keystroke Dynamics Benchmark dataset. The second focused on data preprocessing. In the third phase, new keystroke features were engineered from the original dataset. The fourth phase involved feature selection across various types: unigraph (Hold), digraph (Down-Down, Down-Up, Up-Down, Up-Up), trigraph (Hold-Tri), and their combinations. Training and testing were conducted in the fifth and sixth phases using a Support Vector Machine (SVM) classifier, leveraging keystroke patterns for behavioral biometric identification. The final phase focused on evaluating the models. Each model was tested under two scenarios: one where only the first user is treated as the authorized user, and another where the first three users are considered authorized. Each scenario was further divided into two cases based on preprocessing conditions. The models were assessed using multiple performance metrics, including Accuracy, F1-Score, Recall, Precision, ROC-AUC, and Equal Error Rate (EER). The highest achieved results were Accuracy of 99.35%, F1-Score of 94.2%, Recall of 91.8%, Precision of 98.8%, ROC-AUC of 99.56%, and a minimum EER of 0.02. These outcomes demonstrate the effectiveness of the proposed approach in enhancing authentication reliability using keystroke dynamics.
Behavioral biometric , Cybersecurity , Feature engineering , Machine learning , Keystroke dynamics
[1] O. G. Olufemi and R. D. Alimi, "Authenticating Device Users via Keyboard Strokes," International Journal of Computer Applications, vol. 175, no. 17, p. 8887, 2020.
[2] N. Ali, M. M. Hoobi and D. F. Saffo, "Development of Robust and Efficient Symmetric Random Keys Model based on the Latin Square Matrix," Mesopotamian Journal of Cybersecurity, vol. 4, no. 3, pp. 203-215, 2024.
[3] A. J. Smith and B. L. Johnson, "A Comprehensive Review of Cryptographic Techniques for Secure Communication," Journal of Information Security and Applications, vol. 65, pp. 102-114, 2023. doi: 10.1016/j.jisa.2023.102114.
[4] M. M. Hoobi, "Enhanced rail-fence cryptography algorithm using hybrid models," in AIP, Erbil, Iraq, 2025.
[5] R. M. Al-Amri, D. N. Hamood and A. K. Farhan, "Theoretical background of cryptography," Mesopotamian Journal of CyberSecurity, vol. 2023, pp. 7-15, 2023.
[6] X. Lu, S. Zhang, P. Hui and P. Lio, "Continuous authentication by free-text keystroke based on CNN and RNN," Computers & Security, vol. 96, p. 101861, 2020.
[7] A. S. Elmaghraby and Y. Zheng, "Cybersecurity enhancement using recurrent neural networks and keystroke dynamics," in SPIE, online, 2021.
[8] Olga-Dimitra Asvesta, Eleni Vrochidou and George A. Papakostas, "IKDD: A Keystroke Dynamics Dataset for User Classification," Information, vol. 15, p. 511, 2024.
[9] A. A. Wahab, D. Hou, S. Schuckers and A. Barbir, "Utilizing Keystroke Dynamics as Additional Security Measure to Protect Account Recovery Mechanism," in ICISSP, online, 2021.
[10] A. Arsh, N. Kar, S. Das and S. Deb, "Multiple approaches towards authentication using keystroke dynamics," in Procedia Computer Science, India, 2024.
[11] A. M. Gedikli and M. O. Efe, "A simple authentication method with multilayer feedforward neural network using keystroke dynamics," in Springer International Publishing, Istanbul, Turkey, 2020.
[12] E. Maiorana, H. Kalita and P. Campisi, "Deepkey: Keystroke dynamics and CNN for biometric recognition on mobile devices," in IEEE, Roma, Italy, 2019.
[13] G. Zhao, J. Yang, J. Chen, G. Zhu, Z. Jiang, X. Liu and B. Zhang, "Keystroke dynamics identification based on triboelectric nanogenerator for intelligent keyboard using deep learning method," Advanced Materials Technologies, vol. 4, no. 1, p. 1800167, 2019.
[14] K. Elliot, J. Graham, Y. Yassin, T. Ward, J. Caldwell and T. Attie, "A comparison of machine learning algorithms in keystroke dynamics," in 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2019.
[15] T. Ramu, K. Suthendran and T. Arivoli, "Machine learning based soft biometrics for enhanced keystroke recognition system," Multimedia Tools and Applications, vol. 79, no. 15, pp. 10029-10045, 2020.
[16] K. W. Tse and K. Hung, "User behavioral biometrics identification on mobile platform using multimodal fusion of keystroke and swipe dynamics and recurrent neural network," in 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE), Malaysia, 2020.
[17] L. A. Gabralla, "Dense Deep Neural Network Architecture for Keystroke Dynamics Authentication in Mobile Phone," Adv. Sci. Technol. Eng. Syst. J., vol. 5, no. 6, pp. 307-314, 2020.
[18] A. Landowska and A. KoĊakowska, "Keystroke dynamics patterns while writing positive and negative opinions," Sensors, vol. 21, no. 17, p. 5963, September 2021.
[19] A. Thakare, S. Gondane, N. Prasad and S. Chigale, "A machine learning-based approach to password authentication using keystroke biometrics," in Machine Learning, Deep Learning and Computational Intelligence for Wireless Communication: Proceedings of MDCWC 2020, Singapore, 2021.
[20] A. Rahman, M. E. Chowdhury, A. Khandakar, S. Kiranyaz, K. S. Zaman, M. Reaz and M. A. Kadir, "Multimodal EEG and keystroke dynamics based biometric system using machine learning algorithms," IEEE Access, vol. 9, pp. 94625-94643, 2021.
[21] H. C. Chang, J. Li and M. Stamp, "Machine Learning-Based Analysis of Free-Text Keystroke Dynamics," in Artificial Intelligence for Cybersecurity, Cham: Springer, Springer International Publishing, 2022, pp. 331--356.
[22] S. Kar, A. Bamotra, B. Duvvuri and R. Mohanan, "KeyDetect--Detection of anomalies and user based on Keystroke Dynamics," arXiv, vol. 1, p. 2304.03958, 2023.
[23] T. Xi, I. Kuzminykh, B. Ghita and T. Bakhshi, "Evaluating Learning Algorithms for Keystroke Based User Authentication," in 2023 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom), Istanbul, Turkiye, 2023.
[24] S. Roy, J. Pradhan, A. Kumar, D. Adhikary, U. Roy, D. Sinha and R. K. Pal, "A systematic literature review on latest keystroke dynamics based models," IEEE Access, vol. 10, pp. 92192-92236, 2022.
[25] K. S. Killourhy and R. A. Maxion, "Comparing anomaly-detection algorithms for keystroke dynamics," in 2009 IEEE/IFIP International Conference on Dependable Systems & Networks, Lisbon, Portugal, 2009.
[26] S. Szeghalmy and A. Fazekas, "A comparative study of the use of stratified cross-validation and distribution-balanced stratified cross-validation in imbalanced learning," Sensors, vol. 23, no. 4, p. 2333, 2023.
[27] S. Sulaiman, I. Ibraheem and S. Hameed, "Credit Card Fraud Detection Using Improved Deep Learning Models," Computers, Materials & Continua, vol. 78, no. 1, pp. 1049-1069, 2024.
[28] Y. Zheng, L. Yu, S. Haque, P. Zhang and A. S. Elmaghraby, "Improving cybersecurity through deep learning on keystroke and mouse dynamics," in Multimodal Image Exploitation and Learning 2022, Florida, 2022.
[29] S. Haboubi and O. B. Salem, "Energy Consumption Prediction of Smart Buildings by Using Machine Learning Techniques," Iraqi Journal of Science, vol. 64, no. 12, pp. 6509-6521, 2023.
[30] M. Al-jumaili and J. Bazzi, "Cyber-Attack Detection for Cloud-Based Intrusion Detection Systems," Mesopotamian Journal of CyberSecurity, vol. 2023, pp. 170-182, 2023.
[31] M. Aljabri, A. Shaahid, F. Alnasser, A. Saleh, D. Alomari, M. Aboulnour and A. Althubaity, "IoT Attacks Detection Using Supervised Machine Learning Techniques," HighTech and Innovation Journal, vol. 5, no. 3, pp. 534-550, 2024.
